---
title: "7 open-source tools that turn text into voiceover audio"
slug: "open-source-tts"
description: "Seven open-source text-to-speech tools that run on your machine — from instant CPU narration to voice cloning you can train."
published: "2026-11-11"
verifiedAt: "2026-11-11"
picks: 7
canonical: "https://aifree.dev/best/open-source-tts"
---

# 7 open-source tools that turn text into voiceover audio

> Seven open-source text-to-speech tools that run on your machine — from instant CPU narration to voice cloning you can train.

Published 2026-11-11. Last checked 2026-11-11.

Voice actors and per-character cloud APIs price out most hobby videos. These seven open-source text-to-speech tools run on your own machine — instant narration, or a clone of a voice you own.

Every pick has public model weights, a commit in the last 90 days (checked 2026-11-11) and an install from its own docs. One uses a custom license, flagged below. Clone only voices you have permission to use. Ordered from desktop app to toolkit.

## The 7 tools at a glance

| Tool | What it does | Price | Install |
| --- | --- | --- | --- |
| Voicebox | Desktop voice studio: clone, generate, dictate | Free · OSS (MIT) | Download page |
| kokoro-onnx | Fast speech on CPU from the Kokoro model | Free · OSS (MIT) | `pip install -U kokoro-onnx` |
| F5-TTS | Zero-shot cloning from a short clip | Free · OSS (MIT) | `pip install f5-tts` |
| VoxCPM | Multilingual speech + creative voice design | Free · OSS (Apache-2.0) | `pip install voxcpm` |
| GPT-SoVITS | Clone a voice you fine-tune from 1 minute | Free · OSS (MIT) | conda + `install.sh` |
| IndexTTS-2.5 | Controlled narration: emotion, speed, pronunciation | Free · custom license | clone + `uv sync` |
| Coqui TTS | The toolkit: 1,100+ languages, training included | Free · OSS (MPL-2.0) | `uv pip install coqui-tts` |

## 1. Voicebox: the voice studio app

[Voicebox](https://github.com/jamiepine/voicebox) is a desktop app (macOS, Windows) that wraps several TTS engines in one interface: import or create voices, generate speech, dictate into other apps, all running locally.

![Voicebox app showing a voice library, a "Generate speech using Prime…" box with engine picker, and an audio player](https://f.aifree.dev/media/best/open-source-tts/7b9d37288871b251.webp#w=1280&h=767)

**What:** Voice cloning across 8 engines, sound tags like `[laugh]`, audio effects, and texts up to 50,000 characters.

**Why:** Everything the pip tools below do, without writing any code.

**Use when:** You want an app, not a terminal.

**Install:** Download the DMG or MSI from [voicebox.sh](https://voicebox.sh).

**Catch:** No prebuilt Linux app: downloads cover macOS and Windows, and Linux users build from source.

## 2. kokoro-onnx: fast speech on any CPU

[kokoro-onnx](https://github.com/thewh1teagle/kokoro-onnx) runs the small Kokoro model through onnxruntime: near real-time on an M1 Mac, about 300 MB (80 MB quantized), several languages and voices.

**What:** A lightweight Python library that turns text into spoken audio without a GPU.

**Why:** The fastest route from script to audio on a plain laptop.

**Use when:** You need narration in one of its built-in voices, not a clone.

**Install:**

```bash
pip install -U kokoro-onnx
```

**Catch:** Fixed voice set — no cloning — and the ONNX model plus voice files download separately from the release page.

## 3. F5-TTS: zero-shot cloning in one pip

[F5-TTS](https://github.com/SWivid/F5-TTS) clones a voice from a short reference clip with no training step.

**What:** A Python CLI and web UI that take reference audio plus a script and emit matching speech.

**Why:** No dataset, no fine-tune — seconds of reference audio are the whole setup.

**Use when:** You want a specific voice quickly and one-off.

**Install:**

```bash
pip install f5-tts
```

**Catch:** You install the right PyTorch wheel for your platform first (CUDA, ROCm, or CPU) — the README lists one per setup.

## 4. VoxCPM: expressive speech and voice design

[VoxCPM](https://github.com/openbmb/VoxCPM) is a 2B-parameter speech model for 30 languages. Describe a voice in words and it generates one, or clone a voice from reference audio, with 48 kHz output.

![VoxCPM architecture diagram with text-semantic and residual acoustic language models, voice design, and cloning modes](https://f.aifree.dev/media/best/open-source-tts/2a94f502a288459d.webp#w=1280&h=749)

**What:** A pip-installable model that handles plain TTS, cloning, and inventing voices from a text description.

**Why:** Voice design is the part the cloners skip — no reference audio needed.

**Use when:** You need a voice nobody has a recording of.

**Install:**

```bash
pip install voxcpm
```

**Catch:** The docs require Python 3.10 to 3.12 and CUDA 12 or newer, so plan on an NVIDIA GPU.

## 5. GPT-SoVITS: train one voice properly

[GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS) fine-tunes a model on as little as 1 minute of a voice. Its WebUI also builds the dataset: it removes background music, slices the audio, then transcribes and labels it.

**What:** A WebUI for cloning voices you can keep improving, from a minute of clean audio.

**Why:** Zero-shot clones drift on long scripts; a fine-tuned model holds the timbre.

**Use when:** One voice matters enough to spend an hour on it.

**Install:**

```bash
conda create -n GPTSoVits python=3.10
conda activate GPTSoVits
bash install.sh --device CPU --source HF
```

**Catch:** GPU training on Macs gives much lower quality, so the README trains on CPU there. Windows gets a one-click package.

## 6. IndexTTS-2.5: narration you can direct

[IndexTTS](https://github.com/index-tts/index-tts) clones a voice from one reference clip, then lets you direct it: emotion, speed from 0.5× to 2.0×, and pronunciation via Pinyin, CMU phonemes or Japanese kana. Version 2.5 speaks Chinese, English, Japanese, Spanish and Arabic.

**What:** A controllable TTS engine with a vLLM recipe for serving it in production.

**Why:** Duration and emotion control is what raw cloning models leave to chance.

**Use when:** The read has to hit specific pacing and tone, take after take.

**Install:**

```bash
git clone https://github.com/index-tts/index-tts && cd index-tts && uv sync --all-extras
```

**Catch:** Ships under the bilibili Model Use License, not an OSI license — read the terms before any commercial use.

## 7. Coqui TTS: the 1,100-language toolkit

[Coqui TTS](https://github.com/idiap/coqui-ai-TTS), a maintained fork of the original, now-unmaintained Coqui repo, is a Python toolkit: pretrained models in 1,100+ languages, XTTSv2 cloning in 17 languages with streaming under 200 ms, voice conversion, and training recipes.

**What:** A Python toolkit with command-line and API access, plus the code to train or fine-tune your own models.

**Why:** For many languages or a custom model, you need a toolkit, not an app.

**Use when:** You are building a product or covering languages the others skip.

**Install:**

```bash
uv pip install coqui-tts
```

**Catch:** Expect to write Python; there is no GUI. It is a community fork, and the original Coqui repo gets no updates.

## Which one to try first

Want an app instead of a terminal → #1. Just narration in a fixed voice → #2. Clone a voice in five minutes → #3. Build a voice that holds up on long scripts → #5. Many languages or a custom model → #7. If you would rather use cloud APIs on free credits, that is our [free AI voice generator guide](https://aifree.dev/learn/free-ai-voice-generator).

## Picks

1. [Voicebox](https://github.com/jamiepine/voicebox)
2. [kokoro-onnx](https://github.com/thewh1teagle/kokoro-onnx)
3. [F5-TTS](https://github.com/SWivid/F5-TTS)
4. [VoxCPM](https://github.com/openbmb/VoxCPM)
5. [GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS)
6. [IndexTTS-2.5](https://github.com/index-tts/index-tts)
7. [Coqui TTS](https://github.com/idiap/coqui-ai-TTS)

## Frequently asked questions

### What is the best open-source text-to-speech?

It depends on the job: VoxCPM or IndexTTS-2.5 for controllable quality, F5-TTS or GPT-SoVITS for cloning a specific voice, Voicebox if you want a desktop app, kokoro-onnx for fast CPU narration.

### Can open-source TTS clone a voice?

Yes. F5-TTS clones zero-shot from a short reference clip, GPT-SoVITS fine-tunes from about 1 minute of audio, and VoxCPM clones from reference audio or designs new voices from a description. Only clone voices you have permission to use.

### Does open-source TTS run offline?

Yes — all seven tools here run locally on your machine once their models have downloaded. kokoro-onnx needs about 300 MB (80 MB quantized), while the bigger models want a GPU.

## Sources

- https://github.com/jamiepine/voicebox
- https://voicebox.sh
- https://github.com/thewh1teagle/kokoro-onnx
- https://github.com/SWivid/F5-TTS
- https://github.com/openbmb/VoxCPM
- https://github.com/RVC-Boss/GPT-SoVITS
- https://github.com/index-tts/index-tts
- https://github.com/idiap/coqui-ai-TTS

HTML page: https://aifree.dev/best/open-source-tts